Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection
Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited with promoting core features of the construct over spurious artifacts that happen to correlate with it. Yet, over-relying on core features may lead to unintended model bias. Especially, construct-driven CAD -- perturbations of core features -- may induce models to ignore the context in which core features are used. Here, we test models for sexism and hate speech detection on challenging data: non-hateful and non-sexist usage of identity and gendered terms. In these hard cases, models trained on CAD, especially construct-driven CAD, show higher false-positive rates than models trained on the original, unperturbed data. Using a diverse set of CAD -- construct-driven and construct-agnostic -- reduces such unintended bias.
Code (0)
등록된 구현이 없습니다.
Tasks
Hate Speech DetectionSimilar Papers 제목 키워드 기반
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand the contents of natural videos? Standar…
Language ModellingLarge Language ModelRetrievalVideo UnderstandingPairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robu…
Contrastive LearningcounterfactualSustainable Modular Debiasing of Language Models
Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technolo…
FairnessLanguage ModelingLanguage ModellingCounterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---whil…
counterfactualNatural Language InferenceNatural Language UnderstandingReading ComprehensionLimitations of Pinned AUC for Measuring Unintended Bias
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric.…
General Classification